From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents

TL;DR

This paper introduces Agentic Deep Research, a new paradigm leveraging reasoning-enabled Large Language Models to improve complex information retrieval through autonomous, iterative, and dynamic search and synthesis processes.

Contribution

It formalizes the concept of Agentic Deep Research, introduces a test-time scaling law for reasoning depth, and demonstrates superior performance over traditional search methods with benchmark results.

Findings

Agentic Deep Research significantly outperforms traditional search approaches.

A formal scaling law links computational depth to reasoning effectiveness.

Open-source resources support the adoption of this new paradigm.

Abstract

Information retrieval is a cornerstone of modern knowledge acquisition, enabling billions of queries each day across diverse domains. However, traditional keyword-based search engines are increasingly inadequate for handling complex, multi-step information needs. Our position is that Large Language Models (LLMs), endowed with reasoning and agentic capabilities, are ushering in a new paradigm termed Agentic Deep Research. These systems transcend conventional information search techniques by tightly integrating autonomous reasoning, iterative retrieval, and information synthesis into a dynamic feedback loop. We trace the evolution from static web search to interactive, agent-based systems that plan, explore, and learn. We also introduce a test-time scaling law to formalize the impact of computational depth on reasoning and search. Supported by benchmark results and the rise of open-source implementations, we demonstrate that Agentic Deep Research not only significantly outperforms existing approaches, but is also poised to become the dominant paradigm for future information seeking. All the related resources, including industry products, research papers, benchmark datasets, and open-source implementations, are collected for the community in https://github.com/DavidZWZ/Awesome-Deep-Research.